© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129210
    Prev
    Next
    INDEX
    Explanations

    citing or based on justification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ओन
    -0.05
     chaque
    -0.05
    कारात्मक
    -0.05
     [
    -0.05
     sprach
    -0.05
     他
    -0.05
    探讨
    -0.05
    检索
    -0.05
    ждается
    -0.05
     reality
    -0.05
    POSITIVE LOGITS
     значительно
    0.07
     activities
    0.07
     गतिविधियों
    0.07
     eventualmente
    0.06
     mainly
    0.06
     acquist
    0.06
     znacz
    0.06
     증가
    0.06
    蹺
    0.06
     possibly
    0.06
    Activations Density 0.002%

    No Known Activations